Oil field resource allocation using machine learning and optimization
AssigneeSchlumberger Technology Corporation
InventorsAbdulfattah Fahham, Richard James Stuart Booth
Life of this patent
Estimating the term…
Abstract
Oil field resources are allocated using machine learning and optimization. A well of a set of wells is identified. A user interface is presented to obtain a priority of a set of priorities. A schedule is generated for a set of resources for a job using the priority. A job schedule is presented that includes a set of jobs for the set of wells. The job schedule is generated using the set of priorities. An update to the priority is obtained. An updated job schedule is presented based on the update to the priority.
Claims18
A method implemented by at least one data processor having processor-implemented instructions, the method comprising:
- using a machine learning model to determine a set of priorities corresponding to a set of jobs, wherein each job of the set of jobs comprises a defined set of tasks to modify equipment at one or more wellsites, wherein the machine learning model determines a priority for a given job of the set of jobs based on features of the given job;
- generating a job schedule for the set of jobs, wherein the job schedule is generated using the set of priorities;
- presenting a user interface that includes the job schedule, wherein the user interface is configured to enable a user to update the job schedule and update the set of priorities corresponding to the set of jobs of the job schedule by user input that reorders the set of jobs as presented by the user interface to adjust the priorities for the set of jobs;
- generating updates to the set of priorities from user interaction with the user interface;
- and
- using the updates to the set of priorities generated from user interaction with the user interface to update and train the machine learning model for subsequent use in generating priorities for additional jobs based on the features of the additional jobs and in presentation of job schedules derived therefrom.
A system comprising:
- a server with a memory coupled to a processor;
- the memory comprising an operations framework, wherein the operations framework executes on the processor, uses the memory, and is configured for:
- using a machine learning model to determine a set of priorities corresponding to a set of jobs, wherein each job of the set of jobs comprises a defined set of tasks to modify equipment at one or more wellsites, wherein the machine learning model determines a priority for a given job of the set of jobs based on features of the given job;
- generating a job schedule for the set of jobs, wherein the job schedule is generated using the set of priorities;
- presenting a user interface that includes the job schedule, wherein the user interface is configured to enable a user to update the job schedule and update the set of priorities corresponding to the set of jobs of the job schedule by user input that reorders the set of jobs as presented by the user interface to adjust the priorities for the set of jobs;
- generating updates to the set of priorities from user interaction with the user interface;
- and
- using the updates to the set of priorities generated from user interaction with the user interface to update and train the machine learning model for subsequent use in generating priorities for additional jobs based on the features of the additional jobs and in presentation of job schedules derived therefrom.
Dependencies are inferred from the claim text.